Papers with WMT dataset
Secoco: Self-Correcting Encoding for Neural Machine Translation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) is a challenging field due to the wide variety of noises in real-world scenarios. |
| Approach: | They propose a framework that explicitly deals with noisy inputs for robust neural machine translation by introducing self-correcting predictors. |
| Outcome: | The proposed framework can correct noisy inputs and delete specific errors with the translation decoding process. |
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned (P19-1)
Copied to clipboard
| Challenge: | et al., 2017) show that multi-head attention is important for neural machine translation. |
| Approach: | They evaluate the contribution made by individual attention heads to the overall performance of the Transformer model and analyze the roles played by them in the encoder. |
| Outcome: | The proposed pruning method removes the vast majority of heads without affecting performance. |
Lost in Translation: Benchmarking Commercial Machine Translation Models for Dyslexic-Style Text (2025.findings-acl)
Copied to clipboard
| Challenge: | Dyslexia affects writing, leading to unique patterns such as letter and homophone swapping. |
| Approach: | They examine the fairness of four commercial machine translation systems towards dyslexic text through a systematic audit using both synthetically generated and real writing from individuals with dyslexia. |
| Outcome: | The proposed system audits show that it is fair to use synthetic and synthetic dyslexic text and real writing from people with dyslexia. |